Author:
Charkoftaki Georgia,Aalizadeh Reza,Santos-Neto Alvaro,Tan Wan Ying,Davidson Emily A.,Nikolopoulou Varvara,Wang Yewei,Thompson Brian,Furnary Tristan,Chen Ying,Wunder Elsio A.,Coppi Andreas,Schulz Wade,Iwasaki Akiko,Pierce Richard W.,Cruz Charles S. Dela,Desir Gary V.,Kaminski Naftali,Farhadian Shelli,Veselkov Kirill,Datta Rupak,Campbell Melissa,Thomaidis Nikolaos S.,Ko Albert I.,Grubaugh Nathan,Nelson Allison,Wyllie Anne L.,Casanovas-Massana Arnau,White Elizabeth B.,Chiorazzi Michael,Rainone Michael,Earnest Rebecca,Lapidus Sarah,Lim Joseph,Nakahata Maura,Nunez Angela,Shepard Denise,Matos Irene,Strong Yvette,Anastasio Kelly,Brower Kristina,Kuang Maxine,Muenker M. Catherine,Moore Adam J.,Rahming Harold,Glick Laura,Silva Erin,Bermejo Santos,Vijayakumar Pavithra,Geng Bertie,Fournier John,Minasyan Maksym,Bickerton Sean,Linehan Melissa,Wong Patrick,Goldman-Israelow Benjamin,Martin Anjelica,Rice Tyler,Khoury-Hanold William,Nouws Jessica,McDonald David,Rose Kadi-Ann,Cao Yiyun,Sharma Lokesh,Smolgovsky Mikhail,Obaid Abeer,DeIuliis Giuseppe,Park Hong-Jai,Sonnert Nicole,Velazquez Sofia,Peng Xiaohua,Askenase Michael H.,Todeasa Codruta,Bucklin Molly L.,Batsu Maria,Robertson Alexander,Balkcom Natasha,Liu Yicong,Lin Zitong,Dorgay Coriann,Borg Ryan,Di Giuseppe Erendira Carmen,Young H. Patrick,Herbst Roy S.,Thompson David C.,Vasiliou Vasilis,
Abstract
AbstractOver the last century, outbreaks and pandemics have occurred with disturbing regularity, necessitating advance preparation and large-scale, coordinated response. Here, we developed a machine learning predictive model of disease severity and length of hospitalization for COVID-19, which can be utilized as a platform for future unknown viral outbreaks. We combined untargeted metabolomics on plasma data obtained from COVID-19 patients (n = 111) during hospitalization and healthy controls (n = 342), clinical and comorbidity data (n = 508) to build this patient triage platform, which consists of three parts: (i) the clinical decision tree, which amongst other biomarkers showed that patients with increased eosinophils have worse disease prognosis and can serve as a new potential biomarker with high accuracy (AUC = 0.974), (ii) the estimation of patient hospitalization length with ± 5 days error (R2 = 0.9765) and (iii) the prediction of the disease severity and the need of patient transfer to the intensive care unit. We report a significant decrease in serotonin levels in patients who needed positive airway pressure oxygen and/or were intubated. Furthermore, 5-hydroxy tryptophan, allantoin, and glucuronic acid metabolites were increased in COVID-19 patients and collectively they can serve as biomarkers to predict disease progression. The ability to quickly identify which patients will develop life-threatening illness would allow the efficient allocation of medical resources and implementation of the most effective medical interventions. We would advocate that the same approach could be utilized in future viral outbreaks to help hospitals triage patients more effectively and improve patient outcomes while optimizing healthcare resources.
Funder
Yale School of Public Health, Yale University
National Institutes of Health
Publisher
Springer Science and Business Media LLC
Subject
Drug Discovery,Genetics,Molecular Biology,Molecular Medicine